Hugging Face's logo

Spaces:
textgeflecht
/
inference-benchmarking-results-phi4-200-tokens
Running

App Files Community
textgeflecht commited on
Commit
74ef1b0
·
verified ·
1 Parent(s): 34789cc

Upload microsoft_phi-4_2025-05-28-15-47-19.json

Browse files
Files changed (1) hide show
  1. results/microsoft_phi-4_2025-05-28-15-47-19.json +296 -0
results/microsoft_phi-4_2025-05-28-15-47-19.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "max_vus": 800,
4
+ "duration_secs": 120,
5
+ "benchmark_kind": "Rate",
6
+ "warmup_duration_secs": 30,
7
+ "rates": [
8
+ 1.0,
9
+ 10.0,
10
+ 30.0,
11
+ 100.0
12
+ ],
13
+ "num_rates": 10,
14
+ "prompt_options": {
15
+ "num_tokens": 200,
16
+ "min_tokens": 180,
17
+ "max_tokens": 220,
18
+ "variance": 10
19
+ },
20
+ "decode_options": {
21
+ "num_tokens": 200,
22
+ "min_tokens": 180,
23
+ "max_tokens": 220,
24
+ "variance": 10
25
+ },
26
+ "tokenizer": "microsoft/phi-4",
27
+ "model_name": "phi-4",
28
+ "profile": null,
29
+ "meta": null,
30
+ "run_id": "llama.cpp -np 64 -fa -c 32768: unsloth/phi-4-GGUF:Q8_0 (200 tokens)"
31
+ },
32
+ "results": [
33
+ {
34
+ "id": "warmup",
35
+ "executor_type": "ConstantVUs",
36
+ "config": {
37
+ "max_vus": 1,
38
+ "duration_secs": 30,
39
+ "rate": null
40
+ },
41
+ "total_requests": 13,
42
+ "total_tokens": 2469,
43
+ "token_throughput_secs": 85.84032167475472,
44
+ "duration_ms": 28762,
45
+ "time_to_first_token_ms": {
46
+ "p50": 43.505,
47
+ "p60": 43.785,
48
+ "p70": 44.091,
49
+ "p80": 44.589,
50
+ "p90": 44.819,
51
+ "p95": 113.603,
52
+ "p99": 196.091,
53
+ "avg": 56.756
54
+ },
55
+ "inter_token_latency_ms": {
56
+ "p50": 11.402,
57
+ "p60": 11.423,
58
+ "p70": 11.43,
59
+ "p80": 11.44,
60
+ "p90": 11.446,
61
+ "p95": 11.45,
62
+ "p99": 11.455,
63
+ "avg": 11.4
64
+ },
65
+ "failed_requests": 0,
66
+ "successful_requests": 13,
67
+ "request_rate": 0.4519741521959543,
68
+ "total_tokens_sent": 2600,
69
+ "e2e_latency_ms": {
70
+ "p50": 2359.994,
71
+ "p60": 2415.749,
72
+ "p70": 2423.291,
73
+ "p80": 2432.327,
74
+ "p90": 2437.795,
75
+ "p95": 2448.941,
76
+ "p99": 2461.874,
77
+ "avg": 2212.306
78
+ }
79
+ },
80
+ {
81
+ "id": "[email protected]/s",
82
+ "executor_type": "ConstantArrivalRate",
83
+ "config": {
84
+ "max_vus": 800,
85
+ "duration_secs": 120,
86
+ "rate": 1.0
87
+ },
88
+ "total_requests": 115,
89
+ "total_tokens": 22141,
90
+ "token_throughput_secs": 187.3687041837537,
91
+ "duration_ms": 118168,
92
+ "time_to_first_token_ms": {
93
+ "p50": 79.825,
94
+ "p60": 83.058,
95
+ "p70": 88.025,
96
+ "p80": 90.693,
97
+ "p90": 93.539,
98
+ "p95": 96.782,
99
+ "p99": 98.74,
100
+ "avg": 76.993
101
+ },
102
+ "inter_token_latency_ms": {
103
+ "p50": 20.349,
104
+ "p60": 20.547,
105
+ "p70": 20.667,
106
+ "p80": 20.83,
107
+ "p90": 20.991,
108
+ "p95": 21.041,
109
+ "p99": 21.15,
110
+ "avg": 19.804
111
+ },
112
+ "failed_requests": 0,
113
+ "successful_requests": 115,
114
+ "request_rate": 0.9731900537975555,
115
+ "total_tokens_sent": 23000,
116
+ "e2e_latency_ms": {
117
+ "p50": 3988.995,
118
+ "p60": 4116.539,
119
+ "p70": 4168.816,
120
+ "p80": 4298.579,
121
+ "p90": 4383.721,
122
+ "p95": 4450.146,
123
+ "p99": 4547.268,
124
+ "avg": 3877.19
125
+ }
126
+ },
127
+ {
128
+ "id": "[email protected]/s",
129
+ "executor_type": "ConstantArrivalRate",
130
+ "config": {
131
+ "max_vus": 800,
132
+ "duration_secs": 120,
133
+ "rate": 10.0
134
+ },
135
+ "total_requests": 350,
136
+ "total_tokens": 66356,
137
+ "token_throughput_secs": 562.8995505371688,
138
+ "duration_ms": 117882,
139
+ "time_to_first_token_ms": {
140
+ "p50": 21509.027,
141
+ "p60": 30855.205,
142
+ "p70": 36235.461,
143
+ "p80": 45982.228,
144
+ "p90": 53228.865,
145
+ "p95": 59058.001,
146
+ "p99": 65294.203,
147
+ "avg": 24868.085
148
+ },
149
+ "inter_token_latency_ms": {
150
+ "p50": 102.368,
151
+ "p60": 106.643,
152
+ "p70": 110.897,
153
+ "p80": 117.316,
154
+ "p90": 122.404,
155
+ "p95": 125.438,
156
+ "p99": 145.247,
157
+ "avg": 100.561
158
+ },
159
+ "failed_requests": 4,
160
+ "successful_requests": 346,
161
+ "request_rate": 2.935126356107366,
162
+ "total_tokens_sent": 69200,
163
+ "e2e_latency_ms": {
164
+ "p50": 41618.142,
165
+ "p60": 51230.678,
166
+ "p70": 58378.078,
167
+ "p80": 68537.015,
168
+ "p90": 76499.395,
169
+ "p95": 80350.831,
170
+ "p99": 84912.986,
171
+ "avg": 44046.262
172
+ }
173
+ },
174
+ {
175
+ "id": "[email protected]/s",
176
+ "executor_type": "ConstantArrivalRate",
177
+ "config": {
178
+ "max_vus": 800,
179
+ "duration_secs": 120,
180
+ "rate": 30.0
181
+ },
182
+ "total_requests": 360,
183
+ "total_tokens": 65728,
184
+ "token_throughput_secs": 556.2621901079556,
185
+ "duration_ms": 118160,
186
+ "time_to_first_token_ms": {
187
+ "p50": 32321.559,
188
+ "p60": 43632.202,
189
+ "p70": 51940.135,
190
+ "p80": 63969.689,
191
+ "p90": 72681.379,
192
+ "p95": 77960.403,
193
+ "p99": 90786.611,
194
+ "avg": 35401.064
195
+ },
196
+ "inter_token_latency_ms": {
197
+ "p50": 106.179,
198
+ "p60": 109.964,
199
+ "p70": 112.534,
200
+ "p80": 116.693,
201
+ "p90": 121.2,
202
+ "p95": 127.806,
203
+ "p99": 283.587,
204
+ "avg": 105.825
205
+ },
206
+ "failed_requests": 4,
207
+ "successful_requests": 356,
208
+ "request_rate": 3.0128611805993213,
209
+ "total_tokens_sent": 71200,
210
+ "e2e_latency_ms": {
211
+ "p50": 52400.988,
212
+ "p60": 63945.453,
213
+ "p70": 73308.714,
214
+ "p80": 85174.682,
215
+ "p90": 95634.538,
216
+ "p95": 101118.945,
217
+ "p99": 107319.948,
218
+ "avg": 54074.657
219
+ }
220
+ },
221
+ {
222
+ "id": "[email protected]/s",
223
+ "executor_type": "ConstantArrivalRate",
224
+ "config": {
225
+ "max_vus": 800,
226
+ "duration_secs": 120,
227
+ "rate": 100.0
228
+ },
229
+ "total_requests": 183,
230
+ "total_tokens": 32897,
231
+ "token_throughput_secs": 275.4497427446807,
232
+ "duration_ms": 119430,
233
+ "time_to_first_token_ms": {
234
+ "p50": 62326.037,
235
+ "p60": 69299.057,
236
+ "p70": 75980.152,
237
+ "p80": 81953.606,
238
+ "p90": 87866.436,
239
+ "p95": 90864.271,
240
+ "p99": 97108.121,
241
+ "avg": 62262.595
242
+ },
243
+ "inter_token_latency_ms": {
244
+ "p50": 126.036,
245
+ "p60": 127.051,
246
+ "p70": 128.048,
247
+ "p80": 129.197,
248
+ "p90": 130.995,
249
+ "p95": 133.985,
250
+ "p99": 150.687,
251
+ "avg": 126.063
252
+ },
253
+ "failed_requests": 9,
254
+ "successful_requests": 174,
255
+ "request_rate": 1.4569187232141059,
256
+ "total_tokens_sent": 34800,
257
+ "e2e_latency_ms": {
258
+ "p50": 86281.441,
259
+ "p60": 92367.619,
260
+ "p70": 99403.778,
261
+ "p80": 105125.513,
262
+ "p90": 111632.918,
263
+ "p95": 114663.377,
264
+ "p99": 117530.115,
265
+ "avg": 85951.466
266
+ }
267
+ }
268
+ ],
269
+ "start_time": "2025-05-28T15:32:49.890650642+00:00",
270
+ "end_time": "2025-05-28T15:47:19.049425535+00:00",
271
+ "system": {
272
+ "cpu": [
273
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu0@4699MHz",
274
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu1@4699MHz",
275
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu2@4699MHz",
276
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu3@4699MHz",
277
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu4@4699MHz",
278
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu5@4699MHz",
279
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu6@4699MHz",
280
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu7@4699MHz",
281
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu8@4699MHz",
282
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu9@4699MHz",
283
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu10@4699MHz",
284
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu11@4699MHz",
285
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu12@4699MHz",
286
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu13@4699MHz",
287
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu14@4699MHz",
288
+ "AMD Ryzen 7 9800X3D 8-Core Processor cpu15@4699MHz"
289
+ ],
290
+ "memory": "83.47 GB",
291
+ "os_name": "Debian GNU/Linux",
292
+ "os_version": "11",
293
+ "kernel": "5.15.167.4-microsoft-standard-WSL2",
294
+ "hostname": "computer"
295
+ }
296
+ }